An enhanced scheduling approach in a distributed parallel environment using mobile agents

Proceedings 16th Annual International Symposium on High Performance Computing Systems and Applications Pub Date : 2002-06-16 DOI:10.1109/HPCSA.2002.1019152

M. Dantas, J. G. R. C. Lopes, T. G. Ramos

{"title":"An enhanced scheduling approach in a distributed parallel environment using mobile agents","authors":"M. Dantas, J. G. R. C. Lopes, T. G. Ramos","doi":"10.1109/HPCSA.2002.1019152","DOIUrl":null,"url":null,"abstract":"Our goal is to apply mobile agent technology to provide a better scheduling for MPI applications executing in a cluster configuration. This approach could represent in a distributed cluster environment an enhancement on the load balancing of the parallel processes. MPI in a cluster of heterogeneous machines could lead parallel programmers to obtain frustrated results, mainly because of the lack of an even distribution of the workload in the cluster. As a result, before submitting a MPI application to a cluster, we use our JOTA mobile agent approach to acquire a more precise information of machine's workload. Therefore, with a more precise knowledge of the load and characteristics in each machine, we are ready to gather lightweight workstations to form a cluster. Our empirical results indicate that it is possible to spend less elapsed time when considering the execution of a parallel application using the agent approach in comparison to an ordinary MPI environment.","PeriodicalId":111862,"journal":{"name":"Proceedings 16th Annual International Symposium on High Performance Computing Systems and Applications","volume":"426 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2002-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"11","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings 16th Annual International Symposium on High Performance Computing Systems and Applications","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/HPCSA.2002.1019152","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 11

Abstract

Our goal is to apply mobile agent technology to provide a better scheduling for MPI applications executing in a cluster configuration. This approach could represent in a distributed cluster environment an enhancement on the load balancing of the parallel processes. MPI in a cluster of heterogeneous machines could lead parallel programmers to obtain frustrated results, mainly because of the lack of an even distribution of the workload in the cluster. As a result, before submitting a MPI application to a cluster, we use our JOTA mobile agent approach to acquire a more precise information of machine's workload. Therefore, with a more precise knowledge of the load and characteristics in each machine, we are ready to gather lightweight workstations to form a cluster. Our empirical results indicate that it is possible to spend less elapsed time when considering the execution of a parallel application using the agent approach in comparison to an ordinary MPI environment.

查看原文本刊更多论文

使用移动代理的分布式并行环境中的增强调度方法

我们的目标是应用移动代理技术，为在集群配置中执行的MPI应用程序提供更好的调度。这种方法可以在分布式集群环境中增强并行进程的负载平衡。异构机器集群中的MPI可能会导致并行程序员获得令人沮丧的结果，这主要是因为集群中缺乏工作负载的均匀分布。因此，在向集群提交MPI应用程序之前，我们使用JOTA移动代理方法来获取机器工作负载的更精确信息。因此，在对每台机器的负载和特性有了更精确的了解之后，我们就可以将轻量级工作站集合起来形成一个集群。我们的经验结果表明，与普通的MPI环境相比，在考虑使用代理方法执行并行应用程序时，可以花费更少的运行时间。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Proceedings 16th Annual International Symposium on High Performance Computing Systems and Applications

自引率

0.00%

发文量